Testrun finished: Lc0 0.22.0 with huge 384x30-t40-1097 S.Vieri Net.
https://www.sp-cc.de
(Perhaps you have to clear your browsercache or reload the website)
SPCC: Testrun of Lc0 384x30-t40-1097 finished
Moderators: hgm, Rebel, chrisw
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: SPCC: Testrun of Lc0 384x30-t40-1097 finished
For me, it becomes more and more clear, that it is the wrong way to build nets, which are bigger size, than the net-size in the training run, which delievered the learning-data. IMHO the other direction is the right way:
Building nets, which are same or smaller size, than the net-size in the training run, which delievered the learning-data.
Means: T40 training was 256x20 size. So any net built out of T40-games should be 256x20 or smaller, not bigger.
T60 training is 320x24. So any net built out of T60-games should be 320x24 or smaller, not bigger.
Building nets, which are same or smaller size, than the net-size in the training run, which delievered the learning-data.
Means: T40 training was 256x20 size. So any net built out of T40-games should be 256x20 or smaller, not bigger.
T60 training is 320x24. So any net built out of T60-games should be 320x24 or smaller, not bigger.
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: SPCC: Testrun of Lc0 384x30-t40-1097 finished
Next NN-testrun: Lc0 0.22.0 with DarkQueen 2.0 Net (first testrun of a net built out of human (online) games, only)
I doubt, that human games are good enough to build a really strong net out of them. But I want to test that...
I doubt, that human games are good enough to build a really strong net out of them. But I want to test that...
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: SPCC: Testrun of Lc0 384x30-t40-1097 finished
How many nodes per second were you getting?pohl4711 wrote: ↑Thu Nov 07, 2019 12:10 pm Testrun finished: Lc0 0.22.0 with huge 384x30-t40-1097 S.Vieri Net.
https://www.sp-cc.de
(Perhaps you have to clear your browsercache or reload the website)
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: SPCC: Testrun of Lc0 384x30-t40-1097 finished
On my mobile RTX 2060 (with reduced speed by afterburner-tool, in order to get a Leela-Ratio of 1.3, because the mobile Hexacore CPU i7-8750H is not so fast (with turbo-boost switched off)), lc0 reaches 11500 n/s in the starting position (wrote this on my website), with a 256x20 net. The 384x30 net is 2.25 times bigger, than a 256x20 net, so around 5100 n/s (chess starting position) are calculated by lc0 on my machine.